Improved data processing features in Foundry IQ: Richer content extraction and data enrichment

2026-06-02 · Source: Microsoft Foundry Blog articles · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Data Science & Analytics, Cloud Computing & IT Infrastructure · Depth: Intermediate, short

Summary

The Microsoft Foundry IQ (Azure AI Search) 2026-05-01-preview release introduces significant enhancements to data processing for enterprise retrieval systems. Key updates include expanded SharePoint indexing to cover modern ASPX site pages and SharePoint Lists, alongside document libraries, with recursive subsite discovery. The platform now offers improved Content Understanding via Foundry Tools, enabling semantic chunking that respects document structure and AI-generated image descriptions to convert visual content into retrievable text, activated by setting contentExtractionMode to "standard". Additionally, image serving preserves and makes extracted images available at retrieval time, allowing models to reason over visual information. Other updates include Azure API Management endpoint support for Azure OpenAI skills and private connectivity for secure model communication. The 2026-04-01 REST API also made several capabilities generally available, such as the GenAI Prompt skill and enhanced Content Understanding.

Key takeaway

For AI Engineers and MLOps teams building enterprise RAG or agentic retrieval systems, you should immediately explore Foundry IQ's 2026-05-01-preview features. Utilizing expanded SharePoint indexing, semantic chunking, and image serving will significantly improve grounding and answer quality by preserving critical document structure and visual context. This reduces custom engineering effort and enhances the reliability of your retrieval systems.

Key insights

Improved data pipelines in Foundry IQ enhance RAG and agentic retrieval by preserving content structure and visual context.

Principles

• Data pipeline quality directly impacts RAG grounding.
• Preserving document structure improves answer quality.
• Visual context is critical for agentic reasoning.

Method

Enable Content Understanding by setting contentExtractionMode property to "standard" in file-based indexed knowledge sources (Azure blob, SharePoint, OneLake) for semantic chunking and AI-generated image descriptions.

In practice

• Index SharePoint ASPX pages and Lists.
• Convert diagrams into retrievable text.
• Provide images for visual reasoning.

Topics

• Foundry IQ
• Azure AI Search
• RAG Systems
• SharePoint Indexing
• Content Understanding
• Image Serving

Best for: CTO, VP of Engineering/Data, Director of AI/ML, AI Engineer, MLOps Engineer, AI Architect

Related on AIssential

• RAG Is Not Dead. You’re Just Building It Wrong. — Optimizing RAG for production requires systematic engineering across all layers, prioritizing retrieval over LLM changes.
• Foundry IQ: New governance and enterprise AI security capabilities — Enterprise AI systems require robust security and governance features to integrate sensitive content while preserving existing access controls.
• Foundry IQ: Improve recall by up to 54% with knowledge bases — Foundry IQ knowledge bases significantly improve agentic retrieval's evidence recall and answer quality while reducing token costs.
• Why Naive Chunking Breaks RAG, and What to Build Instead — Structure-aware parsing and multimodal retrieval techniques are crucial for effective RAG on complex documents.
• How Agentic RAG Works? — Agentic RAG transforms linear retrieval into a decision-making loop, enhancing accuracy for complex queries.
• Enterprise Document Intelligence: A Series on Building RAG Brick by Brick, from Minimal to Corpus scale — Enterprise RAG success hinges on deep document and domain expertise, not just advanced AI models.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Microsoft Foundry Blog articles.